From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from foss.arm.com (usa-sjc-mx-foss1.foss.arm.com [217.140.101.70]) by dpdk.org (Postfix) with ESMTP id BA2141B722 for ; Wed, 25 Oct 2017 09:14:17 +0200 (CEST) Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.72.51.249]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 8D34880D; Wed, 25 Oct 2017 00:14:16 -0700 (PDT) Received: from lenovo-a010984.shanghai.arm.com (lenovo-a010984.shanghai.arm.com [10.169.40.44]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 945B03F246; Wed, 25 Oct 2017 00:14:15 -0700 (PDT) From: Herbert Guan To: dev@dpdk.org, bruce.richardson@intel.com, konstantin.ananyev@intel.com Cc: herbert.guan@arm.com, jianbo.liu@arm.com, phil.yang@arm.com Date: Wed, 25 Oct 2017 15:13:46 +0800 Message-Id: <1508915626-21407-1-git-send-email-herbert.guan@arm.com> X-Mailer: git-send-email 1.8.3.1 Subject: [dpdk-dev] [PATCH] test: provide performance difference ratio and test time X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 25 Oct 2017 07:14:19 -0000 The printed time values presented in TSC is not straight forward showing the performance difference. And if the high resolution counter is not enabled, time value is too small to show the actual performance (e.g. "1 - 1" seems the same but in fact the perfomance diffs by 50% or more). With the performance difference ratio caculated and printed, it'll be easier for people to read and compare the performance between rte_memcpy() and memcpy(). Since the TSC values' units may diff a lot on different platforms, the total execution time of aligned/unaligned memcpy test are provided to allow comparation between platforms. Signed-off-by: Herbert Guan --- test/test/test_memcpy_perf.c | 50 +++++++++++++++++++++++++++++++++----------- 1 file changed, 38 insertions(+), 12 deletions(-) diff --git a/test/test/test_memcpy_perf.c b/test/test/test_memcpy_perf.c index 91de856..b23026b 100644 --- a/test/test/test_memcpy_perf.c +++ b/test/test/test_memcpy_perf.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include @@ -241,8 +242,9 @@ memcpy(dst+dst_addrs[t], src+src_addrs[t], size); \ total_time2 += rte_rdtsc() - start_time; \ } \ - printf("%8.0f -", (double)total_time /TEST_ITERATIONS); \ - printf("%5.0f", (double)total_time2 / TEST_ITERATIONS); \ + printf("%3.0f -", (double)total_time / TEST_ITERATIONS); \ + printf("%3.0f", (double)total_time2 / TEST_ITERATIONS); \ + printf("(%6.2f%%) ", ((double)total_time - total_time2)*100/total_time2); \ } while (0) /* Run aligned memcpy tests for each cached/uncached permutation */ @@ -324,6 +326,9 @@ perf_test(void) { int ret; + struct timeval tv_begin, tv_end; + double time_aligned, time_unaligned; + double time_aligned_const, time_unaligned_const; ret = init_buffers(); if (ret != 0) @@ -340,26 +345,47 @@ do_uncached_write(large_buf_write, 0, small_buf_read, 1, SMALL_BUFFER_SIZE); printf("\n** rte_memcpy() - memcpy perf. tests (C = compile-time constant) **\n" - "======= ============== ============== ============== ==============\n" - " Size Cache to cache Cache to mem Mem to cache Mem to mem\n" - "(bytes) (ticks) (ticks) (ticks) (ticks)\n" - "------- -------------- -------------- -------------- --------------"); + "======= ================= ================= ================= =================\n" + " Size Cache to cache Cache to mem Mem to cache Mem to mem\n" + "(bytes) (ticks) (ticks) (ticks) (ticks)\n" + "------- ----------------- ----------------- ----------------- -----------------"); - printf("\n========================= %2dB aligned ============================", + printf("\n================================= %2dB aligned =================================", alignment_unit); /* Do aligned tests where size is a variable */ + gettimeofday(&tv_begin, NULL); perf_test_variable_aligned(); - printf("\n------- -------------- -------------- -------------- --------------"); + gettimeofday(&tv_end, NULL); + time_aligned = (double)(tv_end.tv_sec - tv_begin.tv_sec) + + ((double)tv_end.tv_usec - tv_begin.tv_usec)/1000000; + printf("\n------- ----------------- ----------------- ----------------- -----------------"); /* Do aligned tests where size is a compile-time constant */ + gettimeofday(&tv_begin, NULL); perf_test_constant_aligned(); - printf("\n=========================== Unaligned ============================="); + gettimeofday(&tv_end, NULL); + time_aligned_const = (double)(tv_end.tv_sec - tv_begin.tv_sec) + + ((double)tv_end.tv_usec - tv_begin.tv_usec)/1000000; + printf("\n================================== Unaligned =================================="); /* Do unaligned tests where size is a variable */ + gettimeofday(&tv_begin, NULL); perf_test_variable_unaligned(); - printf("\n------- -------------- -------------- -------------- --------------"); + gettimeofday(&tv_end, NULL); + time_unaligned = (double)(tv_end.tv_sec - tv_begin.tv_sec) + + ((double)tv_end.tv_usec - tv_begin.tv_usec)/1000000; + printf("\n------- ----------------- ----------------- ----------------- -----------------"); /* Do unaligned tests where size is a compile-time constant */ + gettimeofday(&tv_begin, NULL); perf_test_constant_unaligned(); - printf("\n======= ============== ============== ============== ==============\n\n"); - + gettimeofday(&tv_end, NULL); + time_unaligned_const = (double)(tv_end.tv_sec - tv_begin.tv_sec) + + ((double)tv_end.tv_usec - tv_begin.tv_usec)/1000000; + printf("\n======= ================= ================= ================= =================\n\n"); + + printf("Test Execution Time (seconds):\n"); + printf("Aligned variable copy size = %8.3f\n", time_aligned); + printf("Aligned constant copy size = %8.3f\n", time_aligned_const); + printf("Unaligned variable copy size = %8.3f\n", time_unaligned); + printf("Unaligned constant copy size = %8.3f\n", time_unaligned_const); free_buffers(); return 0; -- 1.8.3.1